diegomarino/claude-toolshed/trim-md

Claude Code and agent skill by diegomarino/claude-toolshed

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Trim markdown for LLM consumption — remove token waste, normalize structure

Install

npx vskill@latest install diegomarino/claude-toolshed/trim-md

SKILL.md

/trim-md

User request: "$ARGUMENTS"

Task

Trim and optimize markdown files for LLM/agent consumption. Run the trim-md script on the given paths, then present the output.

Opt-out

Files containing <!-- trim-md:disable --> on its own line are excluded. The comment must be a standalone line — inline mentions in prose or code blocks are ignored.

Process

Step 1: Resolve skill directory
bash
SKILL_DIR="$(find "$HOME/.claude/plugins/cache" -type d -name "trim-md" -path "*/skills/trim-md" 2>/dev/null | head -1)"
[[ -z "$SKILL_DIR" ]] && SKILL_DIR="$(find "$HOME" -maxdepth 8 -type d -name "trim-md" -path "*/skills/trim-md" 2>/dev/null | head -1)"
echo "SKILL_DIR=$SKILL_DIR"

If SKILL_DIR is empty, stop with: "Could not locate the trim-md skill directory. Ensure the plugin is installed."

Step 2: Ensure dependencies
bash
bash "$SKILL_DIR/scripts/ensure-deps.sh"

If the script exits with an error, show the missing dependency message to the user and stop.

Step 3: Run trim-md

Parse $ARGUMENTS for paths and the dry-run flag.

Dry-run detection: If $ARGUMENTS contains any of these tokens (case-insensitive): dry, dry-run, --dry-run, dryrun — pass --dry-run to the script. Remove the token from the path list.

Remaining arguments are the target paths. If no paths remain, use . (current directory).

bash
bash "$SKILL_DIR/scripts/trim-md.sh" [--dry-run] <paths>
Step 4: Present output

Show the script output to the user as-is. No additional commentary needed unless there were errors.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
44
Repository forks
4
7-day trend score
19

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 18 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/diegomarino/claude-toolshed/trim-md/badge)](https://verified-skill.com/skills/diegomarino/claude-toolshed/trim-md)

Something wrong with this skill or its page? Tell us.